Limits...
Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks.

Molina M, Sanchez-Soriano J, Corcho O - Sensors (Basel) (2015)

Bottom Line: In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions.We present a general method that uses such information to generate sensor descriptions in natural language.The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches.

View Article: PubMed Central - PubMed

Affiliation: Department of Artificial Intelligence, Technical University of Madrid, Campus de Montegancedo S/N, 28660 Boadilla del Monte, Madrid, Spain. martin.molina@upm.es.

ABSTRACT
Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

No MeSH data available.


Related in: MedlinePlus

Geographic distribution of the national hydrological sensor network SAIH (part of the network shown by the website of the Ministry of Environment of Spain).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541865&req=5

sensors-15-16009-f001: Geographic distribution of the national hydrological sensor network SAIH (part of the network shown by the website of the Ministry of Environment of Spain).

Mentions: However, it is not always easy for such communities of users to access and understand data from sensor networks. Datasets are normally represented using technical terminology and professional jargon (sensor devices, code identifiers, physical magnitudes, etc.), which may be unfamiliar to certain users. For example, in Spain, the SAIH system (Sistema Automático de Información Hidrológica) is a national hydrologic sensor network that has been operating for more than 20 years [6] (Figure 1). This network collects real-time hydrological data (water flows, water levels, rainfall, etc.) recorded by thousands of sensors at different locations. The information collected by the SAIH network is useful for different tasks, such as early warnings for floods or water management. Sensors in this network are identified using a set of conventions established by technical operators. For example, the sensor C001L85PQUIN refers to a sensor that measures the accumulated rainfall in hourly intervals at a certain location of the Ebro basin. These types of references can be effectively used by domain experts. However, for the general public, these identifiers and code lists represent an important language barrier that prevents non-experts from an easy understanding of data.


Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks.

Molina M, Sanchez-Soriano J, Corcho O - Sensors (Basel) (2015)

Geographic distribution of the national hydrological sensor network SAIH (part of the network shown by the website of the Ministry of Environment of Spain).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541865&req=5

sensors-15-16009-f001: Geographic distribution of the national hydrological sensor network SAIH (part of the network shown by the website of the Ministry of Environment of Spain).
Mentions: However, it is not always easy for such communities of users to access and understand data from sensor networks. Datasets are normally represented using technical terminology and professional jargon (sensor devices, code identifiers, physical magnitudes, etc.), which may be unfamiliar to certain users. For example, in Spain, the SAIH system (Sistema Automático de Información Hidrológica) is a national hydrologic sensor network that has been operating for more than 20 years [6] (Figure 1). This network collects real-time hydrological data (water flows, water levels, rainfall, etc.) recorded by thousands of sensors at different locations. The information collected by the SAIH network is useful for different tasks, such as early warnings for floods or water management. Sensors in this network are identified using a set of conventions established by technical operators. For example, the sensor C001L85PQUIN refers to a sensor that measures the accumulated rainfall in hourly intervals at a certain location of the Ebro basin. These types of references can be effectively used by domain experts. However, for the general public, these identifiers and code lists represent an important language barrier that prevents non-experts from an easy understanding of data.

Bottom Line: In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions.We present a general method that uses such information to generate sensor descriptions in natural language.The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches.

View Article: PubMed Central - PubMed

Affiliation: Department of Artificial Intelligence, Technical University of Madrid, Campus de Montegancedo S/N, 28660 Boadilla del Monte, Madrid, Spain. martin.molina@upm.es.

ABSTRACT
Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

No MeSH data available.


Related in: MedlinePlus